Creating New Technologies to Bring New Benefits
Our Technology is a result of intensely focused development, and countless hours of real-world testing and validation.
With its advanced sensor systems, the vehicles have the capability to see the environment around it, in 360 degrees, day and night. It is designed to identify pedestrians in a crosswalk, or an object darting suddenly into its path, and to respond accordingly.
We combine LiDAR and camera data for classifying and tracking objects, making high confidence determinations more quickly. This helps, for example, identify pedestrians, vehicle types and road details such as lane lines, construction zones and signage. Our complementary set of long range sensors track high-speed objects, such as oncoming vehicles, and the short-range sensors provide detail about moving objects near the vehicle such as pedestrians and bicycles.
By integrating our Autonomous technology system into the different vehicles, and through close coordination between the hardware and software teams, we have evaluated potential failure modes for all systems, and addressed them throughout development to ensure a safe and reliable product.
In our Autonomous technologies, we have the capabilities to perform the functions necessary to understand the world around the vehicle and make the driving decisions that safely transport passengers. No one technologies make this “brain” work. Instead, the computers use a combination of systems that work safely together, including: Mapping, Simulation, Behavioral Control, Machine Learning, Localization, Planning, Safety, Controls, Networking, Dispatch and Routing, Perception, Remote Assistance.
We have designed and built an Autonomous technology to safely operate among aggressive drivers, bicyclists, delivery trucks, construction, unprotected left turns, stop signs and countless other factors that arise when driving in the city.
Our autonomous technology has the potential to provide a level of safety far beyond the capabilities of humans. As our experience and iterative improvements continue on our system
We combine data gathered from our extensive testing with comprehensive safety analyses to identify additional potential challenges we may not have experienced on the road.
We believe that a safe self-driving car must be built from the ground up, seamlessly integrating the self-driving system into the vehicle. That’s exactly what we did
The DGWorld Autonomous technologies and system are designed to be retrofitted to any kind of vehicle, with a modular and flexible system architecture, adaptable for various autonomous driving applications. Our solution consists of a redundant electrical Drive-by Wire System, Lidar, GNSS, IMU based Localization, Mapping, Lidar, Radar, Vision-based Perception, Safety System, AI Risk Assessment Engine “based on deep learning algorithms” and, Navigation engine.
Drive by Wire System:
Localization and Mapping System:
§ Unique advanced 3D SLAM (6 DoF) technology provides an accurate real-time position over long distances without drift
§ Lidar Sensor based, infrastructure-free algorithm, considering the vehicle dynamics
§ Sensor Fusion with GNSS and IMU for higher system availability and exception handling, as well to increase safety
§ HD Mapping to create reference Map included
§ Automatic update of mapping information and possibility to share these updates with other vehicles
Perception / Safety System:
§ Redundant Sensor Architecture (Fusion) to achieve highest safety standards
§ Classification of Objects and other Vehicles
§ Prediction of the movement of other road users
§ Perception algorithms integrate the data from the sensor over time, in order to build a 3D rich model of the environment that can then be analyzed in search of information of interest in nearly real-time (4ms)
§ Detection of Lanes, Traffic signs, Traffic lights and Speed Limits
§ Active re-routing according to traffic situations
AI Risk Assessment Engine:
§ Computes driving risk 20 times per second
§ Autonomous driving can adapt driving behavior in order to keep risk under a maximum accepted risk value
§ Records risky/safe driving behavior and modifies drive behavior in real time with alerts
§ Alerts before a risky situation if and only if driving behavior is not appropriate to expected driving context (road safety)
§ Field-proven navigation and control solution, which has been validated in real-world Outdoor and Indoor environments and multiple application fields
§ Learning Mode to easily teach new travel routes which can then be recalled anytime